Reviewed-by: Chunming Zhou <david1.zhou at amd.com> for series.
Thanks,
David Zhou
On 2018å¹´08æ??01æ?¥ 19:31, Christian König wrote:
> Instead of the fixed round robin use let the scheduler balance the load
> of page table updates.
>
> Signed-off-by: Christian König <christian.koenig at amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 12 ++----------
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 7 +++----
> drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 12 +++++++-----
> drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 12 +++++++-----
> drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 12 +++++++-----
> drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 12 +++++++-----
> drivers/gpu/drm/amd/amdgpu/si_dma.c | 12 +++++++-----
> 8 files changed, 41 insertions(+), 40 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 745f760b8df9..971ab128f277 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -2335,7 +2335,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
> adev->mman.buffer_funcs = NULL;
> adev->mman.buffer_funcs_ring = NULL;
> adev->vm_manager.vm_pte_funcs = NULL;
> - adev->vm_manager.vm_pte_num_rings = 0;
> + adev->vm_manager.vm_pte_num_rqs = 0;
> adev->gmc.gmc_funcs = NULL;
> adev->fence_context = dma_fence_context_alloc(AMDGPU_MAX_RINGS);
> bitmap_zero(adev->gfx.pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index 015613b4f98b..662e8a34d52c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -2568,9 +2568,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
> struct amdgpu_bo *root;
> const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE,
> AMDGPU_VM_PTE_COUNT(adev) * 8);
> - unsigned ring_instance;
> - struct amdgpu_ring *ring;
> - struct drm_sched_rq *rq;
> unsigned long size;
> uint64_t flags;
> int r, i;
> @@ -2586,12 +2583,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
> INIT_LIST_HEAD(&vm->freed);
>
> /* create scheduler entity for page table updates */
> -
> - ring_instance = atomic_inc_return(&adev->vm_manager.vm_pte_next_ring);
> - ring_instance %= adev->vm_manager.vm_pte_num_rings;
> - ring = adev->vm_manager.vm_pte_rings[ring_instance];
> - rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
> - r = drm_sched_entity_init(&vm->entity, &rq, 1, NULL);
> + r = drm_sched_entity_init(&vm->entity, adev->vm_manager.vm_pte_rqs,
> + adev->vm_manager.vm_pte_num_rqs, NULL);
> if (r)
> return r;
>
> @@ -2898,7 +2891,6 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
> adev->vm_manager.seqno[i] = 0;
>
> - atomic_set(&adev->vm_manager.vm_pte_next_ring, 0);
> spin_lock_init(&adev->vm_manager.prt_lock);
> atomic_set(&adev->vm_manager.num_prt_users, 0);
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
> index 67a15d439ac0..034f8c399c2d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
> @@ -244,10 +244,9 @@ struct amdgpu_vm_manager {
> /* vram base address for page table entry */
> u64 vram_base_offset;
> /* vm pte handling */
> - const struct amdgpu_vm_pte_funcs *vm_pte_funcs;
> - struct amdgpu_ring *vm_pte_rings[AMDGPU_MAX_RINGS];
> - unsigned vm_pte_num_rings;
> - atomic_t vm_pte_next_ring;
> + const struct amdgpu_vm_pte_funcs *vm_pte_funcs;
> + struct drm_sched_rq *vm_pte_rqs[AMDGPU_MAX_RINGS];
> + unsigned vm_pte_num_rqs;
>
> /* partial resident texture handling */
> spinlock_t prt_lock;
> diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> index d0fa2aac2388..154b1499b07e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> @@ -1386,15 +1386,17 @@ static const struct amdgpu_vm_pte_funcs cik_sdma_vm_pte_funcs = {
>
> static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev)
> {
> + struct drm_gpu_scheduler *sched;
> unsigned i;
>
> if (adev->vm_manager.vm_pte_funcs == NULL) {
> adev->vm_manager.vm_pte_funcs = &cik_sdma_vm_pte_funcs;
> - for (i = 0; i < adev->sdma.num_instances; i++)
> - adev->vm_manager.vm_pte_rings[i] =
> - &adev->sdma.instance[i].ring;
> -
> - adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
> + for (i = 0; i < adev->sdma.num_instances; i++) {
> + sched = &adev->sdma.instance[i].ring.sched;
> + adev->vm_manager.vm_pte_rqs[i] =
> + &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
> + }
> + adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
> }
> }
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> index 15ae4bc9c072..c403bdf8ad70 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> @@ -1312,15 +1312,17 @@ static const struct amdgpu_vm_pte_funcs sdma_v2_4_vm_pte_funcs = {
>
> static void sdma_v2_4_set_vm_pte_funcs(struct amdgpu_device *adev)
> {
> + struct drm_gpu_scheduler *sched;
> unsigned i;
>
> if (adev->vm_manager.vm_pte_funcs == NULL) {
> adev->vm_manager.vm_pte_funcs = &sdma_v2_4_vm_pte_funcs;
> - for (i = 0; i < adev->sdma.num_instances; i++)
> - adev->vm_manager.vm_pte_rings[i] =
> - &adev->sdma.instance[i].ring;
> -
> - adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
> + for (i = 0; i < adev->sdma.num_instances; i++) {
> + sched = &adev->sdma.instance[i].ring.sched;
> + adev->vm_manager.vm_pte_rqs[i] =
> + &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
> + }
> + adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
> }
> }
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> index 1e07ff274d73..2677d6a1bf42 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> @@ -1752,15 +1752,17 @@ static const struct amdgpu_vm_pte_funcs sdma_v3_0_vm_pte_funcs = {
>
> static void sdma_v3_0_set_vm_pte_funcs(struct amdgpu_device *adev)
> {
> + struct drm_gpu_scheduler *sched;
> unsigned i;
>
> if (adev->vm_manager.vm_pte_funcs == NULL) {
> adev->vm_manager.vm_pte_funcs = &sdma_v3_0_vm_pte_funcs;
> - for (i = 0; i < adev->sdma.num_instances; i++)
> - adev->vm_manager.vm_pte_rings[i] =
> - &adev->sdma.instance[i].ring;
> -
> - adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
> + for (i = 0; i < adev->sdma.num_instances; i++) {
> + sched = &adev->sdma.instance[i].ring.sched;
> + adev->vm_manager.vm_pte_rqs[i] =
> + &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
> + }
> + adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
> }
> }
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> index e7ca4623cfb9..65883bb5f17b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> @@ -1750,15 +1750,17 @@ static const struct amdgpu_vm_pte_funcs sdma_v4_0_vm_pte_funcs = {
>
> static void sdma_v4_0_set_vm_pte_funcs(struct amdgpu_device *adev)
> {
> + struct drm_gpu_scheduler *sched;
> unsigned i;
>
> if (adev->vm_manager.vm_pte_funcs == NULL) {
> adev->vm_manager.vm_pte_funcs = &sdma_v4_0_vm_pte_funcs;
> - for (i = 0; i < adev->sdma.num_instances; i++)
> - adev->vm_manager.vm_pte_rings[i] =
> - &adev->sdma.instance[i].ring;
> -
> - adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
> + for (i = 0; i < adev->sdma.num_instances; i++) {
> + sched = &adev->sdma.instance[i].ring.sched;
> + adev->vm_manager.vm_pte_rqs[i] =
> + &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
> + }
> + adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
> }
> }
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
> index b75d901ba3c4..fafaf259b17b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
> +++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
> @@ -879,15 +879,17 @@ static const struct amdgpu_vm_pte_funcs si_dma_vm_pte_funcs = {
>
> static void si_dma_set_vm_pte_funcs(struct amdgpu_device *adev)
> {
> + struct drm_gpu_scheduler *sched;
> unsigned i;
>
> if (adev->vm_manager.vm_pte_funcs == NULL) {
> adev->vm_manager.vm_pte_funcs = &si_dma_vm_pte_funcs;
> - for (i = 0; i < adev->sdma.num_instances; i++)
> - adev->vm_manager.vm_pte_rings[i] =
> - &adev->sdma.instance[i].ring;
> -
> - adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
> + for (i = 0; i < adev->sdma.num_instances; i++) {
> + sched = &adev->sdma.instance[i].ring.sched;
> + adev->vm_manager.vm_pte_rqs[i] =
> + &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
> + }
> + adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
> }
> }
>
